Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 2901
    Prev
    Next
    INDEX
    Explanations

    mentions of legislative bills and initiatives

    oai_token-act-pair · gpt-3.5-turbo

    legislative terms and references to bills or legislation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     civilisation
    -0.73
     admission
    -0.69
     Hebdo
    -0.66
     lesson
    -0.65
     prolet
    -0.65
    Pont
    -0.65
     unlaw
    -0.65
     Mubarak
    -0.63
     traged
    -0.62
     discretion
    -0.60
    POSITIVE LOGITS
    osponsors
    1.20
    ospons
    1.17
    HB
    1.07
     sponsored
    1.00
     authored
    0.98
     bills
    0.98
     legislation
    0.98
     Reps
    0.96
     introduced
    0.95
     bill
    0.95
    Activations Density 0.230%

    No Known Activations